Fred Ettish wrote:
 > I was given this problem and and having some difficulty understanding
 > part of it.
 >
 > The problem involves a .250 hitter who gets 5 at bats per game and
 > the question is ( I think) "What is the expected streak of games
 > where the batter gets a hit?"
 >
 > So
 >
 > The probability of not getting a hit at bat is .750. The probability
 > of no hits at 4 at bats is .750^5 = .237 The probability of at least
 > one hit per game is 1 - .237 = .763

You are in good shape up to here, if my assumption of typographical
error is correct (specifically, the above should read "probability
of no hits at 5 at bats")

At this point, to get the expected consecutive number of games in which
a batter gets a hit, you would have a geometric distribution with
probability p=0.763 for each trial. Thus, expected value is 1/p = 
1/0.763 = well you can figure it out from here

 > So the longest streak is k where .763^k=1/162
 >
 > Can anyone explain this last step? Why set it equal to 1/162?

I can't explain it.

 > Thanks

Now, all of this also makes the assumption that the probability of
getting a hit each and every at bat is the same, a dubious assumption, 
but perhaps a place to start.


-- 
Paige Miller
[EMAIL PROTECTED]
http://www.kodak.com

"It's nothing until I call it!" -- Bill Klem, NL Umpire
"When you get the choice to sit it out or dance, I hope you dance" --
Lee Ann Womack

.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to